Automatic Landslide Mapping with Earth Observation Data

该博士项目旨在开发一种新的方法，通过卫星和社交媒体数据的新颖组合，快速自动绘制山体滑坡地图，并在灾害响应活动中常规使用该方法。与诺丁汉大学和英国地质调查局的研究人员合作，该研究项目将寻求使用人工智能从新闻和社交媒体中提取有关山体滑坡事件的信息，然后将其用于开发一种深度学习方法，根据其光谱和地形特征自动绘制山体滑坡地图。然后，成功的申请人将在英国进行实地工作，以验证滑坡测绘结果，并更好地了解可能的触发因素。

This PhD project aims to develop a new approach to rapidly and automatically mapping landslides the novel combination of data from both satellite and social media, with the ambition to routinely use the approach during disaster response activities. Working with researchers at the University of Nottingham and British Geological Survey, the research project will seek to use Artificial Intelligence to extract information on landslide events from news and social media outlets, which will then be used to develop a Deep-Learning method for automatically mapping landslides based on their spectral and topographic characteristics. The successful applicant will then undertake field work in the UK to validate the landslide mapping results and to better understanding possible triggering factors.